Convolutional neural networks on the HEALPix sphere: a pixel-based algorithm and its application to CMB data analysis
Abstract
We describe a novel method for the application of convolutional neural networks (CNNs) to fields defined on the sphere, using the Hierarchical Equal Area Latitude Pixelization scheme (HEALPix). Specifically, we have developed a pixel-based approach to implement convolutional and pooling layers on the spherical surface, similarly to what is commonly done for CNNs applied to Euclidean space. The main advantage of our algorithm is to be fully integrable with existing, highly optimized libraries for NNs (e.g., PyTorch, TensorFlow, etc.). We present two applications of our method: (i) recognition of handwritten digits projected on the sphere; (ii) estimation of cosmological parameter from simulated maps of the cosmic microwave background (CMB). The latter represents the main target of this exploratory work, whose goal is to show the applicability of our CNN to CMB parameter estimation. We have built a simple NN architecture, consisting of four convolutional and pooling layers, and we have used it for all the applications explored herein. Concerning the recognition of handwritten digits, our CNN reaches an accuracy of ~95%, comparable with other existing spherical CNNs, and this is true regardless of the position and orientation of the image on the sphere. For CMB-related applications, we tested the CNNmore »
- Authors:
-
- International School for Advanced Studies, Trieste (Italy); Inst. for Fundamental Physics of the Univ., Trieste (Italy)
- Univ. degli Studi di Milano, Milano (Italy); Istituto Nazionale di Fisica Nucleare (INFN), Milano (Italy)
- Publication Date:
- Research Org.:
- Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States). National Energy Research Scientific Computing Center (NERSC)
- Sponsoring Org.:
- USDOE Office of Science (SC)
- OSTI Identifier:
- 1577584
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Astronomy and Astrophysics
- Additional Journal Information:
- Journal Volume: 628; Journal ID: ISSN 0004-6361
- Publisher:
- EDP Sciences
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 79 ASTRONOMY AND ASTROPHYSICS; Astronomy & Astrophysics; Abstract; Full HTML; PDF (2.726 MB); ePUB (6.803 MB); References; NASA ADS Abstract Service
Citation Formats
Krachmalnicoff, N., and Tomasi, M. Convolutional neural networks on the HEALPix sphere: a pixel-based algorithm and its application to CMB data analysis. United States: N. p., 2019.
Web. doi:10.1051/0004-6361/201935211.
Krachmalnicoff, N., & Tomasi, M. Convolutional neural networks on the HEALPix sphere: a pixel-based algorithm and its application to CMB data analysis. United States. doi:10.1051/0004-6361/201935211.
Krachmalnicoff, N., and Tomasi, M. Tue .
"Convolutional neural networks on the HEALPix sphere: a pixel-based algorithm and its application to CMB data analysis". United States. doi:10.1051/0004-6361/201935211. https://www.osti.gov/servlets/purl/1577584.
@article{osti_1577584,
title = {Convolutional neural networks on the HEALPix sphere: a pixel-based algorithm and its application to CMB data analysis},
author = {Krachmalnicoff, N. and Tomasi, M.},
abstractNote = {We describe a novel method for the application of convolutional neural networks (CNNs) to fields defined on the sphere, using the Hierarchical Equal Area Latitude Pixelization scheme (HEALPix). Specifically, we have developed a pixel-based approach to implement convolutional and pooling layers on the spherical surface, similarly to what is commonly done for CNNs applied to Euclidean space. The main advantage of our algorithm is to be fully integrable with existing, highly optimized libraries for NNs (e.g., PyTorch, TensorFlow, etc.). We present two applications of our method: (i) recognition of handwritten digits projected on the sphere; (ii) estimation of cosmological parameter from simulated maps of the cosmic microwave background (CMB). The latter represents the main target of this exploratory work, whose goal is to show the applicability of our CNN to CMB parameter estimation. We have built a simple NN architecture, consisting of four convolutional and pooling layers, and we have used it for all the applications explored herein. Concerning the recognition of handwritten digits, our CNN reaches an accuracy of ~95%, comparable with other existing spherical CNNs, and this is true regardless of the position and orientation of the image on the sphere. For CMB-related applications, we tested the CNN on the estimation of a mock cosmological parameter, defining the angular scale at which the power spectrum of a Gaussian field projected on the sphere peaks. We estimated the value of this parameter directly from simulated maps, in several cases: temperature and polarization maps, presence of white noise, and partially covered maps. For temperature maps, the NN performances are comparable with those from standard spectrum-based Bayesian methods. For polarization, CNNs perform about a factor four worse than standard algorithms. Nonetheless, our results demonstrate, for the first time, that CNNs are able to extract information from polarization fields, both in full-sky and masked maps, and to distinguish between E and B-modes in pixel space. Lastly, we have applied our CNN to the estimation of the Thomson scattering optical depth at reionization (τ) from simulated CMB maps. Even without any specific optimization of the NN architecture, we reach an accuracy comparable with standard Bayesian methods. This work represents a first step towards the exploitation of NNs in CMB parameter estimation and demonstrates the feasibility of our approach.},
doi = {10.1051/0004-6361/201935211},
journal = {Astronomy and Astrophysics},
number = ,
volume = 628,
place = {United States},
year = {2019},
month = {8}
}
Web of Science
Works referenced in this record:
FERMI LARGE AREA TELESCOPE THIRD SOURCE CATALOG
journal, June 2015
- Acero, F.; Ackermann, M.; Ajello, M.
- The Astrophysical Journal Supplement Series, Vol. 218, Issue 2
The clustering of galaxies in the SDSS-III Baryon Oscillation Spectroscopic Survey: baryon acoustic oscillations in the Data Release 9 spectroscopic galaxy sample
journal, December 2012
- Anderson, L.; Aubourg, E.; Bailey, S.
- Monthly Notices of the Royal Astronomical Society, Vol. 427, Issue 4
Rotation-invariant convolutional neural networks for galaxy morphology prediction
journal, April 2015
- Dieleman, Sander; Willett, Kyle W.; Dambre, Joni
- Monthly Notices of the Royal Astronomical Society, Vol. 450, Issue 2
SkyNet: an efficient and robust neural network training tool for machine learning in astronomy
journal, May 2014
- Graff, Philip; Feroz, Farhan; Hobson, Michael P.
- Monthly Notices of the Royal Astronomical Society, Vol. 441, Issue 2
Enzo: an Adaptive mesh Refinement code for Astrophysics
journal, March 2014
- Bryan, Greg L.; Norman, Michael L.; O'Shea, Brian W.
- The Astrophysical Journal Supplement Series, Vol. 211, Issue 2
A TWO-DIMENSIONAL INFRARED MAP OF THE EXTRASOLAR PLANET HD 189733b
journal, February 2012
- Majeau, Carl; Agol, Eric; Cowan, Nicolas B.
- The Astrophysical Journal, Vol. 747, Issue 2
XSPECT, estimation of the angular power spectrum by computing cross-power spectra with analytical error bars
journal, April 2005
- Tristram, M.; Macias-Perez, J. F.; Renault, C.
- Monthly Notices of the Royal Astronomical Society, Vol. 358, Issue 3
Cosmological parameters from CMB and other data: A Monte Carlo approach
journal, November 2002
- Lewis, Antony; Bridle, Sarah
- Physical Review D, Vol. 66, Issue 10
Computational biology perspective: kernel methods and deep learning: Kernel methods and deep learning
journal, July 2012
- Lodhi, Huma
- Wiley Interdisciplinary Reviews: Computational Statistics, Vol. 4, Issue 5
DeepSphere: Efficient spherical convolutional neural network with HEALPix sampling for cosmological applications
journal, April 2019
- Perraudin, N.; Defferrard, M.; Kacprzak, T.
- Astronomy and Computing, Vol. 27
Neural networks and the separation of cosmic microwave background and astrophysical signals in sky maps
journal, November 2000
- Baccigalupi, C.; Bedini, L.; Burigana, C.
- Monthly Notices of the Royal Astronomical Society, Vol. 318, Issue 3
ANN z : Estimating Photometric Redshifts Using Artificial Neural Networks
journal, April 2004
- Collister, Adrian A.; Lahav, Ofer
- Publications of the Astronomical Society of the Pacific, Vol. 116, Issue 818
Model for Evaluation of Stock Values by Ensemble Model Using Deep Learning [深層学習を用いたアンサンブルモデルによる株主価値推定モデルの提案]
journal, January 2018
- Tamura, Koichiro; Uenoyama, Katsuya; Iitsuka, Shuhei
- Transactions of the Japanese Society for Artificial Intelligence, Vol. 33, Issue 1
Deep convolutional neural network and 3D deformable approach for tissue segmentation in musculoskeletal magnetic resonance imaging: Deep Learning Approach for Segmenting MR Image
journal, July 2017
- Liu, Fang; Zhou, Zhaoye; Jang, Hyungseok
- Magnetic Resonance in Medicine, Vol. 79, Issue 4
Planck 2015 results : I. Overview of products and scientific results
journal, September 2016
- Adam, R.; Ade, P. A. R.; Aghanim, N.
- Astronomy & Astrophysics, Vol. 594
Financial Time Series Prediction Based on Deep Learning
journal, December 2017
- Yan, Hongju; Ouyang, Hongbing
- Wireless Personal Communications, Vol. 102, Issue 2
HEALPix: A Framework for High‐Resolution Discretization and Fast Analysis of Data Distributed on the Sphere
journal, April 2005
- Gorski, K. M.; Hivon, E.; Banday, A. J.
- The Astrophysical Journal, Vol. 622, Issue 2
Deep learning for computational biology
journal, July 2016
- Angermueller, Christof; Pärnamaa, Tanel; Parts, Leopold
- Molecular Systems Biology, Vol. 12, Issue 7
The Transiting Exoplanet Survey Satellite: Simulations of Planet Detections and Astrophysical False Positives
journal, August 2015
- Sullivan, Peter W.; Winn, Joshua N.; Berta-Thompson, Zachory K.
- The Astrophysical Journal, Vol. 809, Issue 1
Neural network techniques for financial performance prediction: integrating fundamental and technical analysis
journal, September 2004
- Lam, Monica
- Decision Support Systems, Vol. 37, Issue 4
NeuCube: A spiking neural network architecture for mapping, learning and understanding of spatio-temporal brain data
journal, April 2014
- Kasabov, Nikola K.
- Neural Networks, Vol. 52
Fast cosmological parameter estimation using neural networks
journal, March 2007
- Auld, T.; Bridges, M.; Hobson, M. P.
- Monthly Notices of the Royal Astronomical Society: Letters, Vol. 376, Issue 1
Polarized CMB power spectrum estimation using the pure pseudo-cross-spectrum approach
journal, June 2009
- Grain, J.; Tristram, M.; Stompor, R.
- Physical Review D, Vol. 79, Issue 12
Measuring the Baryon Acoustic Oscillation scale using the Sloan Digital Sky Survey and 2dF Galaxy Redshift Survey: Measuring the BAO scale
journal, September 2007
- Percival, Will J.; Cole, Shaun; Eisenstein, Daniel J.
- Monthly Notices of the Royal Astronomical Society, Vol. 381, Issue 3
Urinary bladder segmentation in CT urography using deep-learning convolutional neural network and level sets: Bladder segmentation using DL-CNN and level sets
journal, March 2016
- Cha, Kenny H.; Hadjiiski, Lubomir; Samala, Ravi K.
- Medical Physics, Vol. 43, Issue 4
Rapid Bayesian position reconstruction for gravitational-wave transients
journal, January 2016
- Singer, Leo P.; Price, Larry R.
- Physical Review D, Vol. 93, Issue 2
Neural Network Ensemble Based CAD System for Focal Liver Lesions from B-Mode Ultrasound
journal, April 2014
- Virmani, Jitendra; Kumar, Vinod; Kalra, Naveen
- Journal of Digital Imaging, Vol. 27, Issue 4
DeepCMB: Lensing reconstruction of the cosmic microwave background with deep neural networks
journal, July 2019
- Caldeira, J.; Wu, W. L. K.; Nord, B.
- Astronomy and Computing, Vol. 28
A hybrid approach based on neural networks and genetic algorithms for detecting temporal patterns in stock markets
journal, March 2007
- Kim, Hyun-jung; Shin, Kyung-shik
- Applied Soft Computing, Vol. 7, Issue 2
Role of Artificial Intelligence Techniques (Automatic Classifiers) in Molecular Imaging Modalities in Neurodegenerative Diseases
journal, January 2017
- Cascianelli, Silvia; Scialpi, Michele; Amici, Serena
- Current Alzheimer Research, Vol. 14, Issue 2
Observation of High-Energy Astrophysical Neutrinos in Three Years of IceCube Data
journal, September 2014
- Aartsen, M. G.; Ackermann, M.; Adams, J.
- Physical Review Letters, Vol. 113, Issue 10
Earth as an Extrasolar Planet: Earth Model Validation Using EPOXI Earth Observations
journal, June 2011
- Robinson, Tyler D.; Meadows, Victoria S.; Crisp, David
- Astrobiology, Vol. 11, Issue 5